A Configurable Optimization Framework for Volcanic Seismo-Acoustic Event Detection

A critical challenge in volcanic seismology is the human interpretation of complex seismo-acoustic signals, which hinders the development of reliable warning systems for hazards (lahars, for instance) in active regions, such as Costa Rica. Computational methods for early warnings struggle with high background noise and manual parameter tuning, making reliable and reproducible analysis difficult. To address this, we developed a comprehensive computational framework for automated evaluation and optimization of volcanic eruption detectors. The solution proposed performs a seismo-acoustic analysis of time-series data, employing a partial waveform stacking strategy with an adaptive Z-detector as the characteristic function for event triggering. A key contribution of this work is its configurable brute-force optimization strategy, which systematically tunes detector parameters by evaluating the predictions against real-world event catalogs. This approach overcomes significant challenges in this research field, such as manual and suboptimal tuning methods, by measuring the uncertainty of the detection performed with different parameter combinations. Initial experiments on a single day's data from a Costa Rican volcano yielded perfect classification, achieving an F1-score of 1.00. However, scaling the methodology to a full month of data resulted in a significant decrease in performance (F1-score 0.27). Despite the diminished performance on the complete dataset, this preliminary research constitutes a crucial advancement over manual, inefficient tuning methods, offering a more reproducible and analytical approach to the field of volcano-seismology.